SurgicAI: A Hierarchical Platform for Fine-Grained Surgical Policy Learning and Benchmarking

2024-06-19

Neural Information Processing Systems

AI Summary

In robot-assisted surgery, automating high-dexterity tasks—such as suturing—remains challenging due to poor adaptability and limited generalization of existing approaches; current learning platforms lack support for decomposing complex surgical procedures and standardized evaluation. This paper introduces the first hierarchical surgical policy learning platform tailored for the da Vinci surgical system, innovatively integrating task decomposition, modular policy composition, and a unified evaluation benchmark. The platform unifies high-fidelity simulation, expert demonstration collection, reinforcement learning (RL), and imitation learning (IL), underpinned by a standardized data pipeline. We systematically evaluate diverse RL and IL algorithms on suturing tasks, demonstrating the platform’s effectiveness in fine-motor skill acquisition, cross-algorithm fair benchmarking, and policy generalization across scenarios. Our work establishes a scalable methodology and foundational infrastructure for autonomous execution of complex surgical procedures.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Planning, Routing, and Scheduling: Learning for Planning and Scheduling
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Despite advancements in robotic-assisted surgery, automating complex tasks like suturing remain challenging due to the need for adaptability and precision. Learning-based approaches, particularly reinforcement learning (RL) and imitation learning (IL), require realistic simulation environments for efficient data collection. However, current platforms often include only relatively simple, non-dexterous manipulations and lack the flexibility required for effective learning and generalization. We introduce SurgicAI, a novel platform for development and benchmarking addressing these challenges by providing the flexibility to accommodate both modular subtasks and more importantly task decomposition in RL-based surgical robotics. Compatible with the da Vinci Surgical System, SurgicAI offers a standardized pipeline for collecting and utilizing expert demonstrations. It supports deployment of multiple RL and IL approaches, and the training of both singular and compositional subtasks in suturing scenarios, featuring high dexterity and modularization. Meanwhile, SurgicAI sets clear metrics and benchmarks for the assessment of learned policies. We implemented and evaluated multiple RL and IL algorithms on SurgicAI. Our detailed benchmark analysis underscores SurgicAI's potential to advance policy learning in surgical robotics. Details: https://github.com/surgical-robotics-ai/SurgicAI

Problem

• Automating complex surgical tasks
• Realistic simulation environments
• Effective learning and generalization

Innovation

• Flexible platform for surgical robotics.
• Supports RL and IL approaches.
• Standardizes expert demonstration collection.